Interpreting my result in SmartPLS. Please Help

Questions about the implementation and application of the PLS-SEM method, that are not related to the usage of the SmartPLS software.
Post Reply
milkyben91
PLS Junior User
Posts: 2
Joined: Fri May 26, 2017 11:11 am
Real name and title: Benjamin Chua

Interpreting my result in SmartPLS. Please Help

Post by milkyben91 »

Hi Researchers and Scholars,

I recently just managed to compute my survey and came out with a result via SmartPLS. All my constructs are reflective*

I have a few questions to ask regarding my result.

1) I have two latent variables which have loadings less than 0.700 (two out of three to be exact). I have read several forums and journals stating that if i remove one loading >0.700 and the AVE and composite reliability is more than 0.5 or 0.7 respectively i can keep the 2nd loading (which is less than 0.700). Is it right to say so?

2) I have one path loading (give it a name A to B) which was suppose to be negative in my literature review but in SmartPLS algorithm, it turns out that the path coefficient was positive and the t-value was significant. Other than reverse coding it what else can i do to resolve this issue?

It will be of great help for anyone who can assist me with this issue. Thank you so much.
User avatar
cringle
SmartPLS Developer
Posts: 818
Joined: Tue Sep 20, 2005 9:13 am
Real name and title: Prof. Dr. Christian M. Ringle
Location: Hamburg (Germany)
Contact:

Re: Interpreting my result in SmartPLS. Please Help

Post by cringle »

@1: Only delete items with outer loadings below 0.4. If loadings are below 0.7, only delete them if necessary to increase the AVE above 0.4 and the composite reliability above 0.7.

@2: the sign depends on the orientation of your items and your construct. re-scaling could be an option.

Best
CR
Post Reply